Most folks reach for written form content when thinking about the "A" in a RAG architecture. Mixed media really opens up a lot of possibilities, very cool, nice work!
If you share a gist.github.com of your code I'm happy to look. The .toml and .lock files come from Poetry python-poetry.org it's a replacement tool to pip. If you want you can pip install the same packages. I'm also in the langchain discord as @austinbv if you want help dm me there Happy coding!
Thank I was just planning the next video and thinking this. I'll make the font much larger and lose the purple at the bottom so you can see the full terminal better
Most folks reach for written form content when thinking about the "A" in a RAG architecture. Mixed media really opens up a lot of possibilities, very cool, nice work!
The whisper API is a really clean way to get audio into a "rag" consumable format
Pretty cool stuff! I should start diving into the Whisper API for podcast transcription.
You should! We have also been playing with @AssemblyAI for speaker identification and time stamping. Maybe we build something with them next!
Hi! I'm pretty new for this kind of stuff. How do I create those .TOML and .lock files? What should be inside of them?
BTW, I got stuck on the print(load). The error is "JSONDecodeError: Expecting value: line 1 column 1 (char 0)". Got no idea why.
If you share a gist.github.com of your code I'm happy to look.
The .toml and .lock files come from Poetry python-poetry.org it's a replacement tool to pip. If you want you can pip install the same packages.
I'm also in the langchain discord as @austinbv if you want help dm me there
Happy coding!
editor's font size is a little small
Thank I was just planning the next video and thinking this. I'll make the font much larger and lose the purple at the bottom so you can see the full terminal better
I just posted a new video - I increased the font size to 200% let me know if that's better. Thanks!